© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21561
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with variables and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¬
    -0.06
     rend
    -0.06
    itty
    -0.06
     há»Ļ
    -0.06
    ==="
    -0.05
    arien
    -0.05
     kê
    -0.05
    ä¸Ģäºĭ
    -0.05
    į°
    -0.05
    agra
    -0.05
    POSITIVE LOGITS
     Adri
    0.06
    withdraw
    0.06
    ebilecek
    0.05
    иÑĤо
    0.05
     Pou
    0.05
    åѦçļĦ
    0.05
    ÙĨاد
    0.05
    ä¾Ŀæį®
    0.05
    WR
    0.05
    adz
    0.05
    Activations Density 0.028%

    No Known Activations